DEPLOYDatabase

Brain

OneCanvas

OneCanvas (3D Scene Understanding via Panoramic Reprojection) is a 2026 research method from Technical University of Munich and Huawei (Baranowski, Chen, Nießner; NeurIPS 2026 Spotlight) that lifts multi-view RGB-D patch features onto one equirectangular panoramic canvas so a frozen 2D VLM can do 3D scene understanding and situated reasoning with far less training compute than geometry-encoder or large-data alternatives.

Research model · Maturity: Research · Closed

Machine-readable surfaces

Architecture

Frozen VLM vision encoder (Qwen3-VL-8B class) extracts per-view patches; depth + pose lift to 3D; continuous equirectangular canvas tokens with native MRoPE (longitude/latitude/frame) plus additive metric 3D position embedding; LoRA adapters with two-stage spatial curriculum then target QA adaptation.

Key facts

SQA3D 65.3 EM@1 / VSI-Bench 71.3 / SPBench 72.1 zero-shot (research-stated)
Research-stated (research-stated; also arXiv; Robots Digest X): OneCanvas (Baranowski / Chen / Nießner; TUM + Huawei; NeurIPS 2026 Spotlight) reports SOTA spatial reasoning on SQA3D (65.3 EM@1, +2.3 over prior best), VSI-Bench (71.3 average), and SPBench (72.1 zero-shot overall, +4.8), claiming an order of magnitude less training compute than closest competitors. Cap: author project-page / paper tables; not an independent replication.
Panoramic patch-feature canvas for frozen 2D VLMs (research-stated)
Research-stated (research-stated; also arXiv): method lifts multi-view patch features into 3D via depth and camera pose, places each patch as a continuous token on one equirectangular panorama (longitude/latitude from a chosen origin), adds a metric 3D position embedding, and feeds a pretrained VLM (Qwen3-VL-8B class) with LoRA adapters only. Cap: author method description.

Common questions

What is OneCanvas?
OneCanvas (3D Scene Understanding via Panoramic Reprojection) is a 2026 research method from Technical University of Munich and Huawei (Baranowski, Chen, Nießner; NeurIPS 2026 Spotlight) that lifts multi-view RGB-D patch features onto one equirectangular panoramic canvas so a frozen 2D VLM can do 3D scene understanding and situated reasoning with far less training compute than geometry-encoder or large-data alternatives.
Is OneCanvas open source?
No. OneCanvas is recorded as proprietary on the DEPLOY registry. Model weights and source are not publicly available.
What type of AI is OneCanvas?
OneCanvas is a research model, built on a Frozen VLM vision encoder (Qwen3-VL-8B class) extracts per-view patches; depth + pose lift to 3D; continuous equirectangular canvas tokens with native MRoPE (longitude/latitude/frame) plus additive metric 3D position embedding; LoRA adapters with two-stage spatial curriculum then target QA adaptation. architecture on the DEPLOY registry.
What is OneCanvas's maturity stage?
OneCanvas is at the research stage on the DEPLOY maturity ladder. Research stage means active development without commercial deployments on file.
Which robots run on OneCanvas?
No robot models on the DEPLOY registry are recorded as running OneCanvas. DEPLOY wires brain-to-model connections only when the wiring is verifiable from primary sources; absence may reflect pre-deployment or unverified manufacturer claims.

Sources (3)

  1. https://baranowskibrt.github.io/onecanvas/ · 2026
  2. https://arxiv.org/abs/2606.19253 · 2026
  3. https://x.com/robotsdigest/status/2106510045513154969 · 2026-10-03
Methodology: Verified · 3 sources (no primary) · last reviewed 2026-10-10

Verification posture

Verified

Low confidence

Review state

Stable

Last reviewed 2026-10-10

Maturity + lifecycle

Maturity stage: research

Sources by quality tier

2
unclassified
Unclassified source
1
preprint
Preprint

The framework is documented at /methodology. Corrections at /corrections. Reviewer: DEPLOY editorial team.

Methodology surface for OneCanvas.

Canonical ID 3fb71384-65aa-44f5-ae29-d406a68ffedf